Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection

Jiayu Zhang; Chao Qi; Peter Mecha; Yi Zuo; Zongyou Ben; Haolu Liu; Kunjie Chen

doi:10.1186/s13007-022-00969-w

Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection

Plant Methods. 2022 Dec 14;18(1):136. doi: 10.1186/s13007-022-00969-w.

Authors

Jiayu Zhang¹, Chao Qi¹, Peter Mecha¹, Yi Zuo¹, Zongyou Ben¹, Haolu Liu², Kunjie Chen³

Affiliations

¹ College of Engineering, Nanjing Agricultural University, Nanjing, China.
² Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing, China.
³ College of Engineering, Nanjing Agricultural University, Nanjing, China. kunjiechen@njau.edu.cn.

Abstract

Frequency is essential in signal transmission, especially in convolutional neural networks. It is vital to maintain the signal frequency in the neural network to maintain the performance of a convolutional neural network. Due to destructive signal transmission in convolutional neural network, signal frequency downconversion in channels results into incomplete spatial information. In communication theory, the number of Fourier series coefficients determines the integrity of the information transmitted in channels. Consequently, the number of Fourier series coefficients of the signals can be replenished to reduce the information transmission loss. To achieve this, the ArsenicNetPlus neural network was proposed for signal transmission modulation in detecting cassava diseases. First, multiattention was used to maintain the long-term dependency of the features of cassava diseases. Afterward, depthwise convolution was implemented to remove aliasing signals and downconvert before the sampling operation. Instance batch normalization algorithm was utilized to keep features in an appropriate form in the convolutional neural network channels. Finally, the ArsenicPlus block was implemented to generate pseudo high-frequency in the residual structure. The proposed method was tested on the Cassava Datasets and compared with the V2-ResNet-101, EfficientNet-B5, RepVGG-B3g4 and AlexNet. The results showed that the proposed method performed [Formula: see text] in terms of accuracy, 1.2440 in terms of loss, and [Formula: see text] in terms of the F1-score, outperforming the comparison algorithms.

Keywords: Disease detection; Fourier analysis; Instance batch normalization; Multi-attention; Pseudo high-frequency.